In [2]:
import numpy as np
import pandas as pd
In [3]:
data = pd.read_csv("Zara_sales_EDA.csv")
In [4]:
data.head()
Out[4]:
Product ID;Product Position;Promotion;Product Category;Seasonal;Sales Volume;brand;url;name;description;price;currency;terms;section;season;material;origin
0 185102;Aisle;Yes;clothing;Yes;1243;Zara;https:...
1 188771;Aisle;Yes;clothing;No;1429;Zara;https:/...
2 180176;End-cap;Yes;clothing;Yes;1168;Zara;http...
3 112917;Aisle;Yes;clothing;No;1348;Zara;https:/...
4 192936;End-cap;Yes;clothing;Yes;1602;Zara;http...
In [5]:
# Load your dataset correctly using the semicolon (;) as a separator
file_path = "Zara_sales_EDA.csv"
data = pd.read_csv(file_path, sep=';')
In [6]:
data.head()
Out[6]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
In [7]:
data.tail()
Out[7]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
20247 219627 Front of Store Yes clothing No 1754 Zara https://www.zara.com/us/en/suit-jacket-in-100-... CROPPED WASHED T-SHIRT CHARCOAL Running shoes. Upper in a combination of piece... 31.95 USD jeans WOMAN Summer Linen Blend India
20248 219628 Aisle No clothing No 872 Zara https://www.zara.com/us/en/fleece-overshirt-p0... SATIN WOVEN LEATHER SLIDES STONE Slim fit shirt. Round neck and short sleeves. 49.99 USD jackets WOMAN Spring Linen China
20249 219629 Aisle Yes clothing No 1360 Zara https://www.zara.com/us/en/faux-suede-patch-ja... RELAXED CROPPED LEATHER JACKET CHARCOAL Ankle boots. Made of leather with a suede fini... 20.99 USD shoes WOMAN Spring Polyester China
20250 219630 Aisle No clothing No 892 Zara https://www.zara.com/us/en/fine-knit-crop-swea... SLIM BASIC 100% WOOL SWEATER BURGUNDY RETRO SNEAKERS 64.95 USD jackets WOMAN Winter Polyester Spain
20251 219631 Aisle No clothing No 859 Zara https://www.zara.com/us/en/contrasting-patches... KNIT TUXEDO JACKET BURGUNDY Relaxed fit overshirt made of linen fabric. La... 64.99 USD shoes MAN Summer Linen Turkey
In [8]:
data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20252 entries, 0 to 20251
Data columns (total 17 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   Product ID        20252 non-null  int64  
 1   Product Position  20252 non-null  object 
 2   Promotion         20252 non-null  object 
 3   Product Category  20252 non-null  object 
 4   Seasonal          20252 non-null  object 
 5   Sales Volume      20252 non-null  int64  
 6   brand             20252 non-null  object 
 7   url               20252 non-null  object 
 8   name              20251 non-null  object 
 9   description       20250 non-null  object 
 10  price             20252 non-null  float64
 11  currency          20252 non-null  object 
 12  terms             20252 non-null  object 
 13  section           20252 non-null  object 
 14  season            20252 non-null  object 
 15  material          20252 non-null  object 
 16  origin            20252 non-null  object 
dtypes: float64(1), int64(2), object(14)
memory usage: 2.6+ MB
In [9]:
# summary of the dataset
data.describe()
Out[9]:
Product ID Sales Volume price
count 20252.000000 20252.000000 20252.000000
mean 208931.432303 1097.400454 41.949061
std 8961.076507 298.234609 23.380960
min 110075.000000 518.000000 12.000000
25% 204442.750000 849.000000 23.950000
50% 209505.500000 990.000000 35.950000
75% 214568.250000 1364.250000 53.950000
max 219631.000000 1940.000000 134.990000
In [10]:
data.shape
Out[10]:
(20252, 17)
In [11]:
data.columns
Out[11]:
Index(['Product ID', 'Product Position', 'Promotion', 'Product Category',
       'Seasonal', 'Sales Volume', 'brand', 'url', 'name', 'description',
       'price', 'currency', 'terms', 'section', 'season', 'material',
       'origin'],
      dtype='object')
In [12]:
data.dtypes
Out[12]:
Product ID            int64
Product Position     object
Promotion            object
Product Category     object
Seasonal             object
Sales Volume          int64
brand                object
url                  object
name                 object
description          object
price               float64
currency             object
terms                object
section              object
season               object
material             object
origin               object
dtype: object
In [13]:
# Identify categorical and numerical columns
cat_cols = data.select_dtypes(include=['object', 'category']).columns
num_cols = data.select_dtypes(include=['int64', 'float64']).columns

print("Categorical Columns:", cat_cols.tolist())

print("Numerical Columns:", num_cols.tolist())
Categorical Columns: ['Product Position', 'Promotion', 'Product Category', 'Seasonal', 'brand', 'url', 'name', 'description', 'currency', 'terms', 'section', 'season', 'material', 'origin']
Numerical Columns: ['Product ID', 'Sales Volume', 'price']
In [14]:
data.isna()
Out[14]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 False False False False False False False False False False False False False False False False False
1 False False False False False False False False False False False False False False False False False
2 False False False False False False False False False False False False False False False False False
3 False False False False False False False False False False False False False False False False False
4 False False False False False False False False False False False False False False False False False
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
20247 False False False False False False False False False False False False False False False False False
20248 False False False False False False False False False False False False False False False False False
20249 False False False False False False False False False False False False False False False False False
20250 False False False False False False False False False False False False False False False False False
20251 False False False False False False False False False False False False False False False False False

20252 rows × 17 columns

In [15]:
data.isna().any()
Out[15]:
Product ID          False
Product Position    False
Promotion           False
Product Category    False
Seasonal            False
Sales Volume        False
brand               False
url                 False
name                 True
description          True
price               False
currency            False
terms               False
section             False
season              False
material            False
origin              False
dtype: bool
In [16]:
data.isna().any(axis = 1)
Out[16]:
0        False
1        False
2        False
3        False
4        False
         ...  
20247    False
20248    False
20249    False
20250    False
20251    False
Length: 20252, dtype: bool
In [17]:
data.isna().any(axis = 0)
Out[17]:
Product ID          False
Product Position    False
Promotion           False
Product Category    False
Seasonal            False
Sales Volume        False
brand               False
url                 False
name                 True
description          True
price               False
currency            False
terms               False
section             False
season              False
material            False
origin              False
dtype: bool
In [18]:
data.isnull().sum()
Out[18]:
Product ID          0
Product Position    0
Promotion           0
Product Category    0
Seasonal            0
Sales Volume        0
brand               0
url                 0
name                1
description         2
price               0
currency            0
terms               0
section             0
season              0
material            0
origin              0
dtype: int64
In [19]:
data["brand"].value_counts()
Out[19]:
brand
Zara    20252
Name: count, dtype: int64
In [20]:
data[data["description"].isna()]
Out[20]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
60 151925 End-cap No clothing Yes 845 Zara https://www.zara.com/us/en/vintage-effect-leat... VINTAGE EFFECT LEATHER BOMBER JACKET NaN 29.95 USD jackets WOMAN Autumn Cotton Portugal
72 173576 End-cap No clothing Yes 789 Zara https://www.zara.com/us/en/-p04310461.html NaN NaN 22.95 USD jackets MAN Spring Polyester Cambodia
In [21]:
data[~data["description"].isna()]
Out[21]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
20247 219627 Front of Store Yes clothing No 1754 Zara https://www.zara.com/us/en/suit-jacket-in-100-... CROPPED WASHED T-SHIRT CHARCOAL Running shoes. Upper in a combination of piece... 31.95 USD jeans WOMAN Summer Linen Blend India
20248 219628 Aisle No clothing No 872 Zara https://www.zara.com/us/en/fleece-overshirt-p0... SATIN WOVEN LEATHER SLIDES STONE Slim fit shirt. Round neck and short sleeves. 49.99 USD jackets WOMAN Spring Linen China
20249 219629 Aisle Yes clothing No 1360 Zara https://www.zara.com/us/en/faux-suede-patch-ja... RELAXED CROPPED LEATHER JACKET CHARCOAL Ankle boots. Made of leather with a suede fini... 20.99 USD shoes WOMAN Spring Polyester China
20250 219630 Aisle No clothing No 892 Zara https://www.zara.com/us/en/fine-knit-crop-swea... SLIM BASIC 100% WOOL SWEATER BURGUNDY RETRO SNEAKERS 64.95 USD jackets WOMAN Winter Polyester Spain
20251 219631 Aisle No clothing No 859 Zara https://www.zara.com/us/en/contrasting-patches... KNIT TUXEDO JACKET BURGUNDY Relaxed fit overshirt made of linen fabric. La... 64.99 USD shoes MAN Summer Linen Turkey

20250 rows × 17 columns

In [22]:
data[data["name"].isna()]
Out[22]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
72 173576 End-cap No clothing Yes 789 Zara https://www.zara.com/us/en/-p04310461.html NaN NaN 22.95 USD jackets MAN Spring Polyester Cambodia
In [23]:
data.duplicated().sum()
Out[23]:
0
In [24]:
data["Product Category"].value_counts()
Out[24]:
Product Category
clothing    20252
Name: count, dtype: int64
In [25]:
data["Seasonal"].value_counts()
Out[25]:
Seasonal
No     10136
Yes    10116
Name: count, dtype: int64
In [26]:
data["Product Category"].unique()
Out[26]:
array(['clothing'], dtype=object)
In [27]:
data["Product Position"].unique()
Out[27]:
array(['Aisle', 'End-cap', 'Front of Store'], dtype=object)
In [28]:
data["Product Position"].value_counts()
Out[28]:
Product Position
Aisle             7810
End-cap           6791
Front of Store    5651
Name: count, dtype: int64
In [29]:
data["Product ID"].unique()
Out[29]:
array([185102, 188771, 180176, ..., 219629, 219630, 219631], dtype=int64)
In [30]:
data["Product ID"].value_counts()
Out[30]:
Product ID
185102    1
212879    1
212886    1
212885    1
212884    1
         ..
206129    1
206128    1
206127    1
206126    1
219631    1
Name: count, Length: 20252, dtype: int64
In [31]:
data["Promotion"].unique()
Out[31]:
array(['Yes', 'No'], dtype=object)
In [32]:
data["Promotion"].value_counts()
Out[32]:
Promotion
No     11812
Yes     8440
Name: count, dtype: int64
In [33]:
data["name"].unique()
Out[33]:
array(['BASIC PUFFER JACKET', 'TUXEDO JACKET', 'SLIM FIT SUIT JACKET',
       ..., 'RELAXED CROPPED LEATHER JACKET CHARCOAL',
       'SLIM BASIC 100% WOOL SWEATER BURGUNDY',
       'KNIT TUXEDO JACKET BURGUNDY'], dtype=object)
In [34]:
data["name"]
Out[34]:
0                            BASIC PUFFER JACKET
1                                  TUXEDO JACKET
2                           SLIM FIT SUIT JACKET
3                            STRETCH SUIT JACKET
4                            DOUBLE FACED JACKET
                          ...                   
20247            CROPPED WASHED T-SHIRT CHARCOAL
20248           SATIN WOVEN LEATHER SLIDES STONE
20249    RELAXED CROPPED LEATHER JACKET CHARCOAL
20250      SLIM BASIC 100% WOOL SWEATER BURGUNDY
20251                KNIT TUXEDO JACKET BURGUNDY
Name: name, Length: 20252, dtype: object
In [35]:
data["name"].value_counts()
Out[35]:
name
PLAID OVERSHIRT                            8
CONTRASTING PATCHES BOMBER JACKET          5
SUIT JACKET IN 100% LINEN                  5
FAUX SUEDE BOMBER JACKET                   5
FAUX LEATHER JACKET                        5
                                          ..
UTILITY TEXT T-SHIRT BROWN                 1
TEXTURED TEXTURED WEAVE OVERSHIRT BLACK    1
KNIT BASIC KNIT SWEATER BLACK              1
SATIN SUEDE LACELESS SNEAKERS BROWN        1
KNIT TUXEDO JACKET BURGUNDY                1
Name: count, Length: 17215, dtype: int64
In [36]:
data["description"].unique()
Out[36]:
array(['Puffer jacket made of tear-resistant ripstop fabric. High collar and adjustable long sleeves with adhesive straps. Welt pockets at hip. Adjustable hem with side elastics. Front zip closure.',
       'Straight fit blazer. Pointed lapel collar and long sleeves with buttoned cuffs. Welt pockets at hip and interior pocket. Central back vent at hem. Front button closure.',
       'Slim fit jacket. Notched lapel collar. Long sleeves with buttoned cuffs. Welt pocket at chest and flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Slim fit jacket made of viscose blend fabric. Notched lapel collar. Long sleeves with buttoned cuffs. Welt pocket at chest and flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Jacket made of faux leather faux shearling with fleece interior. Tabbed lapel collar. Long sleeves. Zip pockets at hip. Front zip closure.',
       'Relaxed fit jacket. Contrasting lapel collar and long sleeves with buttoned cuffs. Front pouch pockets. Interior pocket. Washed effect. Front zip closure.',
       'Faux leather puffer jacket. High collar and long sleeves with ribbed interior cuffs. Welt pockets at hip. Interior pocket. Adjustable hem with side elastics. Front zip closure.',
       'Straight fit blazer made of linen. Notched lapel collar and long sleeves with buttoned cuffs. Welt pocket at chest and flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Jacket made of Italian wool. Pointed lapel collar and long sleeves with buttoned cuffs. Welt pocket at chest and flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Puffer jacket made of shiny finish technical fabric. Fill is a blend of 80% down and 20% feathers. High collar with adjustable hood and long sleeves with elastic cuffs. Welt pockets at hip and interior pocket. Adjustable hem with side elastics. Front zip closure.',
       'Jacket made of wool blend fabric. Lapel collar and long sleeves. Welt pockets at hip. Front zip closure.',
       'Oversized cropped jacket. Notched lapel collar and long sleeves with buttoned cuffs. Flap pockets at waist ad interior pocket. Front button closure.',
       'Jacket with lapel collar and snap button details. Long sleeves with zip cuffs. Front zip pockets and interior pocket. Asymmetric front closure with metal zipper.',
       'Leather jacket. Cropped length. Lapel collar and long sleeves. Front hidden in-seam pockets. Front zip closure.',
       'Boxy fit jacket. Lapel collar and long sleeves with buttoned cuffs. Welt pockets at hip. Front button closure.',
       'Jacket made of faux leather fabric. Lapel collar with snap button details. Long sleeves with zip cuffs. Front zip pockets at chest and hip. Interior pocket. Asymmetric front closure with metal zipper.',
       'Jacket made of faux suede fabric. Ribbed elastic high collar and long sleeve. Welt pockets at hip. Rib trim. Front zip closure.',
       'Jacket made of denim fabric with padded interior. Rib elastic collar and long sleeves. Welt pockets at hip and interior pocket. Elastic hem. All-over contrasting topstitching details. Front zip closure.',
       'Cropped jacket made with wool blend fabric. High collar and long sleeves with elastic cuffs. Front patch pockets with flaps. Elastic hem. Front snap button closure.',
       'Straight fit blazer made of linen. Notched lapel collar and long sleeves with buttoned cuffs. Flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Lapel collar jacket with long sleeves with buttoned cuffs. Patch pockets with flaps at chest and side pockets at hip. Front hidden button closure.',
       'Cropped jacket with lightly quilted interior. Lapel collar and long sleeves. Flap patch pockets at hip. Washed effect. Rib hems. Front zip closure.',
       'Relaxed fit jacket in leather. Spread collar and long sleeves with slit cuffs with button closure. Patch pockets at hip. Back vents. Front button closure.',
       'Lightweight jacket made of technical fabric. Round neck and long sleeves. Welt pockets at hip. Interior pocket. Rib trim. Front zip closure.',
       'Straight fit jacket made of dense stretch fabric. Notched lapel collar and long sleeves with buttoned cuffs. Welt pocket at chest and flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Jacket made of faux leather fabric. High collar and long sleeves. Welt pockets at hip and interior pocket. Rib trim. Front zip closure.',
       'Varsity jacket made of faux suede fabric. Double welt pockets at hip and interior pocket. Front and back contrasting patch appliqués and embroidery. Rib trim. Front snap button closure.',
       'Overshirt made of stretchy fabric. Lapel collar and long sleeves with snap buttoned cuffs. Chest patch pockets. Front snap button closure.',
       'Jacket made of technical fabric with padded interior. Tonal elastic rib high collar. Long sleeves. Welt pockets at hip and interior pocket. Interior elastic finish. Front zip closure.',
       'Oversized jacket. Notched lapel collar and long sleeves. Flap pockets at hip and interior pocket. Front button closure.',
       'Varsity jacket with elastic collar and long sleeves. Welt pockets at hip and interior pocket. Embroidered appliqué and contrast front and back patches. Rib trim. Front snap button closure.',
       'Varsity jacket with padded interior. Rib elastic collar and long sleeves in contrast faux leather. Double welt pockets at hip and interior pocket. Contrasting patch appliqués at front and back. Rib trim. Front snap button closure.',
       'Jacket with lightly padded interior. Rib collar and long sleeves. Flap pockets at waist. Rib trim. Front asymmetric zip closure.',
       'Faux leather jacket with padded interior. Lapel collar and long sleeves with snap buttoned cuffs. Welt pockets at hip and interior pocket. Elastic hem. Front zip hidden by a snap button flap.',
       'Jacket made of faux leather fabric. Rib elastic collar and long sleeves. Zip pockets with flaps at hip. Interior pocket. Elastic hem. Front zip closure.',
       'Varsity jacket. High collar and long sleeves. Welt pockets at hip and interior pocket. Rib trim. Front snap button closure.',
       'Lapel collar jacket with long sleeves with buttoned cuffs. Flap pockets at chest and welt pockets at hip. Front button closure.',
       'Jacket made of faux suede fabric. Rib elastic collar and long sleeves. Welt pockets at hip. Rib trim. Front zip closure.',
       'Jacket made of suede. Cropped length. Lapel collar and long sleeves. Front hidden in-seam pockets. Front zip closure.',
       'Jacket with lightly padded interior. Contrasting lapel collar. Long sleeves with buttoned cuffs. Washed effect. Double welt pockets at chest and hip. Front zip closure.',
       'Jacket made of textured fabric. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at chest and hidden pockets at hip. Side vents at hem. Front button closure.',
       'Jacket made of dense cotton fabric cut on the bias. Lapel collar and long sleeves with buttoned cuffs. Welt pockets at hip and interior pocket. Cropped length. Front zip closure.',
       'Quilted jacket made of technical fabric. High collar and long sleeves. Flap pocket at chest and hidden in-seam pockets at side hip. Interior pocket. Interior elastic hem. Cropped length. Front zip closure.',
       'Jacket made of technical fabric with quilted interior. Lapel collar and long sleeves. Flap patch pockets at hip. Rib trim. Front button closure.',
       'Jacket made of faux leather fabric. Lapel collar and long sleeves with snap buttoned cuffs. Welt pockets at hip. Front snap button closure.',
       'Denim jacket with lapel collar and long sleeves with buttoned cuffs. Flap pockets at chest and welt pockets at hip. All over washed effect and rips. Front button closure.',
       'Jacket with lightly padded interior. Lapel collar and long sleeves with buttoned cuffs. Flap pockets at chest and welt pockets at hip. Front button closure.',
       'Varsity jacket made of faux suede fabric. Lapel collar and long sleeves. Double welt pockets at hip and interior pocket. Front contrasting patch appliqués and embroidery. Rib trim. Front snap button closure.',
       'Jacket made of technical fabric with padded interior. High collar with front zip closure and long sleeves with elastic strap cuffs. Front and back contrast embroidered text. Zip pockets at hip. Adjustable elastic strap at hem with side zippers and strap.',
       'Boxy bomber jacket. Rib elastic collar and long sleeves. Welt pockets at hip. Elasticized trim. Front zip closure.',
       'Relaxed fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Side hidden in-seam pockets. Front button closure.',
       'Straight fit blazer. Notched lapel collar and long sleeves with buttoned cuffs. Flap pockets at hip. Interior pocket. Central back vent at hem. Front button closure.',
       'Puffer jacket with high collar and adjustable hood. Long sleeves with interior rib cuffs. Welt pockets at hip and interior pocket. Adjustable hem with side elastics. Front zip hidden by a snap button flap.',
       'Padded jacket made of technical fabric. High collar and long sleeves. Welt pockets at hip. Elasticized trim. Front zip closure.',
       'Jacket made of cotton blend fabric. High collar and long sleeves. Welt pockets at hip. Rib trim. Cropped length. Front zip closure.',
       'Jacket made of dense technical fabric. Lapel collar and long sleeves with buttoned cuffs. Multi-functional front pockets. Front zip hidden by a snap button flap.',
       'Oversized jacket made of technical fabric. High collar and long sleeves with pocket detail. Welt pockets at hip and interior pocket. Rib trim. Adjustable asymmetric hem with side zippers. Front zip closure.',
       'Roomy jacket made of lightweight fabric. Lapel collar and long sleeves with elastic cuffs. Contrasting patch appliqués with embroidery at front and back. Front pouch pocket. Elastic hem. Front zip closure.',
       'Jacket made of cotton denim. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at chest and side pockets at hip. Washed effect. Front zip closure.',
       nan,
       'Lapel collar jacket with long sleeves with buttoned cuffs. Flap pockets at chest and welt pockets at hip. All over washed and uneven textured effect. Front button closure.',
       'Jacket made of wool blend fabric. Lapel collar and long sleeves. Welt pockets at hip and interior pocket. Rib trim. Front zip closure.',
       'Jacket made of cotton and linen blend fabric. Lapel collar and long sleeves with buttoned cuffs. Patch pocket at chest and side pockets at hip. Elastic hem. Front zip closure.',
       'Jacket made of faux shearling fabric. Rib elastic collar and long sleeves. Welt pockets at hip and interior pocket. Rib trim. Front zip closure.',
       'Lapel collar jacket with long sleeves. Front pouch pockets. Front zip closure.',
       'Lapel collar jacket with long sleeves with elastic cuffs. Patch pockets at hip. Elastic hem. Front snap button closure.',
       'Jacket made of wool blend fabric. Pointed lapel collar and long sleeves with buttoned cuffs. Welt pockets at chest and flap pockets at hip. Interior pocket. Back vents. Front double breasted button closure.',
       'Full cut jacket with lapel collar and long sleeves. Front button closure.',
       'Cropped overshirt made of contrast double faced fabric. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Adjustable hem with side elastics. Front button closure partially hidden by a flap.',
       'Varsity jacket with stretchy collar and contrasting hood. Long sleeves. Welt pockets at hip and interior pocket. Embroidered appliqué and contrast front and back patches. Rib trim. Front snap button closure.',
       'Cropped jacket. Lapel collar and long sleeves. Front utility pockets with zip closure. Washed effect. Elastic hem. Adjustable hem with side elastics. Front zip closure.',
       'Lapel collar jacket with long sleeves with buttoned cuffs. Chest patch pockets and welt pockets at hip. Front button closure.',
       'Jacket made of technical fabric with padded interior. High collar with foldable interior hood. Long sleeves with interior rib cuffs. Front pockets with hidden zip closure and interior pocket detail. Adjustable hem with side elastics. Front zip hidden by a snap button flap.',
       'Jacket made of waxed finish fabric with lightly padded interior. Contrast fabric lapel collar. Long sleeves. Patch pockets at hip. Interior pocket. Slightly cropped length. Front hidden zip and button closure.',
       'Quilted jacket made of technical fabric. Lapel collar and long sleeves. Welt pockets at hip. Rib trim. Front zip closure.',
       'Jacket made of technical fabric with padded interior. Lapel collar and long sleeves with elastic cuffs. Welt pockets at hip and interior pocket. Adjustable drawstring hem. Front snap button closure.',
       'Slightly cropped denim jacket. Lapel collar and long sleeves with buttoned cuffs. Flap patch pocket at chest and side hip. Washed effect. Front button closure.',
       'Boxy fit jacket. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at hip. Washed effect.Asymmetric hem with side vents. Front button closure.',
       'Jacket made of faux shearling fabric. V-neckline and long sleeves with elastic cuffs. Lined interior with structured mesh fabric. Welt pockets at hip. Adjustable hem with side elastics. Front snap button closure.',
       'Jacket with lightly padded interior. Corduroy lapel collar. Long sleeves. Patch pockets at hip. Front button closure.',
       'Cropped overshirt. Lapel collar and long sleeves with buttoned cuffs. Front patch pockets. Irregular finished seams. Front button closure.',
       'Vest made of viscose and wool blend fabric. V-neckline. Patch pockets at hip. Front zip closure.',
       'Jacket made of technical fabric with padded interior. High collar and long sleeves with elastic cuffs. Front pockets with hidden zip closure. Elastic hem. Front zip closure.',
       'Parka made of technical fabric with padded interior. High collar with removable hood. Long sleeves with interior elastic cuffs. Welt pockets at chest and flap pockets at hip. Interior pocket. Adjustable interior waistband with drawstring. Adjustable hem with side elastics. Front zip hidden by a snap button flap.',
       'Straight fit jacket made of wool blend fabric. Notched lapel collar and long sleeves with buttoned cuffs. Welt pockets at chest and flap pockets at hip. Interior pocket. Central vent at back hem. Front button closure.',
       'Cotton knit jacket. Hooded collar and long sleeves. Rib trim. Front pouch pockets. Rib trim. Front zip closure.',
       'Jacket made of technical fabric with brushed interior. High collar with adjustable hood. Long sleeves with cuffs and adhesive straps. Zip pockets at chest and hip. Front zip closure.',
       'Straight fit blazer. Notched lapel collar and long sleeves with buttoned cuffs. Welt pocket at chest and flap pockets at hip. Interior pocket. Back vents. Front button closure.',
       'Jacket with padded interior. Rib elastic collar and long sleeves. Flap pockets at hip and interior pocket. Rib trim. Front zip closure.',
       'Cropped jacket made of technical fabric. Hooded high collar and long sleeves with adjustable snap button cuffs. Front patch pockets with flaps at hips. Adjustable hem with side elastics. Front zip hidden by a snap button flap.',
       'Jacket made of technical fabric. High collar with adjustable drawstring hood. Long sleeves with rib cuffs. Chest welt pocket and hip patch pockets. Interior pocket. Adjustable hem with elastics at sides. Front zip hidden by a snap button flap.',
       'Jacket made of technical fabric. Lapel collar and long sleeves with pocket detail. Welt pockets at hip and interior pocket. Washed effect. Elasticized trim. Front zip hidden by a snap button flap.',
       'Jacket made of technical fabric. High collar and long sleeves with adjustable cuffs with snap button straps. Flap patch pockets at hip. Adjustable drawstring hem. Washed effect. Front zip hidden by a snap button flap.',
       'Puffer vest made of technical fabric. Fill is a blend of 60% down and 40% feather. Sleeveless design with high collar. Zip pockets at hip and interior pocket. Adjustable hem with side elastics. Front snap button closure.',
       'Jacket made of technical fabric with lightly padded interior. Rib elastic collar and long sleeves. Zip pockets at hip. Elastic hem. Front zip closure.',
       'Regular fit jacket with lapel collar and long sleeves. Patch pockets at chest and hip. Front button closure.',
       'Jacket made of technical fabric with lightly padded interior. Rib high collar. Long sleeves with elastic cuffs. Patch pockets at hip. Front zip closure.',
       'Boxy fit jacket. High collar with adjustable hood and long sleeves with buttoned cuffs. Patch pockets with flaps at chest. Front straps with multi-functional ring. Washed effect. Front hidden zip and snap button closure.',
       'Cropped jacket made of cotton with waxed finish. Lapel collar and long adjustable cuffed sleeves. Welt pockets at hip and interior pocket. Adjustable front drawcord hem. Front zip closure.',
       'Cropped jacket made with wool blend fabric. Lapel collar and long sleeves. Welt pockets at hip. Front hidden button closure.',
       'Boxy fit overshirt. Lapel collar and short sleeves. Front snap button closure.',
       'Regular fit overshirt made of 22% wool fabric. Lapel collar and long sleeves with buttoned cuffs. Patch pocket at chest and side pockets at hip. Side vents at hem. Front button closure.',
       'Relaxed fit overshirt made with cotton fabric. Lapel collar and long sleeves with buttoned cuffs. Flap patch pockets at chest and side hip pockets. Front button closure.',
       'Relaxed fit reversible overshirt. Italian collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.',
       'Relaxed fit overshirt made with cotton fabric. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at hip. Washed effect. Front button closure.',
       'Relaxed fit overshirt. Lapel collar and long sleeves with adjustable button cuffs. Welt pockets at hip. Front zip hidden by a snap button flap.',
       'Relaxed fit overshirt made of linen fabric. Lapel collar and long sleeves with buttoned cuffs. Chest patch pockets. Front button closure.',
       'Relaxed fit overshirt made of viscose blend fabric. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.',
       'Boxy fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Chest patch pockets. Washed effect. Front button closure.',
       'Relaxed fit overshirt. Lapel collar and long sleeves. Chest patch pocket. Front snap button closure.',
       'Regular fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Front zip closure.',
       'Overshirt made of diagonal textured cotton fabric. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at hip. Front button closure.',
       'Relaxed fit overshirt made of 25% wool fabric. Lapel collar and long sleeves with buttoned cuffs. Patch pocket at chest and side pockets at hip. Front button closure.',
       'Relaxed fit overshirt made of stretch fabric. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.',
       'Cropped overshirt. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Irregular trim. Front button closure.',
       'Overshirt with lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.',
       'Relaxed fit overshirt made of wool blend fabric. Lapel collar and long sleeves with buttoned cuffs. Welt pockets at hip. Front zip closure.',
       'Relaxed fit overshirt made with cotton fabric. Lapel collar and long sleeves with buttoned cuffs. Welt pockets at hip. Front button closure.',
       'Relaxed fit overshirt. Lapel collar and long sleeves with snap button cuffs. Chest patch pockets. Side vents at hem. Front snap button closure.',
       'Overshirt with quilted interior. Lapel collar and long sleeves with buttoned cuffs. Flap patch pockets at chest and in-seam pockets at side hip. Front snap button closure.',
       'Regular fit overshirt made of cotton. Lapel collar and long sleeves with buttoned cuffs. Chest patch pockets. Front button closure.',
       'Relaxed fit overshirt made with cotton fabric. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Contrasting topstitching all over the garment. Front button closure.',
       'Regular fit overshirt with quilted interior. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at chest and welt pockets at hip. Front button closure.',
       'Regular fit overshirt with lightly padded interior. Lapel collar and long sleeves with buttoned cuffs. Flap pockets at hip. Front button closure.',
       'Relaxed fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.',
       'Fisherman sandals. Made of leather with a suede finish. Crossed straps at front. Buckled ankle strap closure. Slightly chunky soles.',
       'Running shoes. Upper in a combination of pieces and finishes. Front zip closure. Back pull tab for ease. Chunky soles with irregular design.',
       'Slip on sneakers. Made of leather with a suede finish. Upper in a combination of pieces. Chunky sole.',
       'Sneakers. Combination of colors and pieces at upper. Lacing with six pairs of eyelets. Chunky rubber sole with irregular design.',
       'Running shoes. Upper in a combination of pieces and materials. Lacing with seven pairs of eyelets. Chunky lug soles. Retro-inspired design.',
       'High top sneakers. Upper in a combination of pieces and materials. Lacing with seven pairs of eyelets. Chunky tonal sole.',
       'Sandals. Made of leather with a suede finish. Two crossed wide straps at instep. Thick lightweight soles.',
       'Sneakers. Upper in a combination of pieces and colors. Lacing with seven pairs of eyelets. Chunky sole with a combination of colors. Retro-inspired design.',
       'Sneakers. Pieces and topstitching at upper. Lacing with six pairs of eyelets. Contrasting slightly chunky soles.',
       'Sneakers. Upper in a combination of pieces and materials. Lacing with seven pairs of eyelets. Quilted back piece. Chunky sole. Retro style.',
       'High-top sneakers. Upper in a combination of pieces. Laces with ten pairs of eyelets. Chunky sole.',
       'Sneakers. Upper in a combination of pieces and colors. Lacing with six pairs of eyelets. Textured chunky soles. Retro style.',
       'Loafers. Made of leather. Smooth upper with ruching at toe. Decorative fringed tassels at instep. Rounded shape. Welt around upper. Chunky lug soles.',
       'Suede leather boots. Ridged seam detail at upper. Lacing with two pairs of eyelets. Welt around upper. Slightly chunky sole.',
       'Sandals with two straps. The thin straps hug the instep. Slightly chunky sole.',
       'Sneakers. Made of leather. Combination of finishes and materials at upper. Lacing with seven pairs of eyelets. Chunky sole in a combination of colors. Retro-inspired design.',
       'Lace-up boots. Upper in a combination of pieces and finishes. Laces with metal appliqués and seven pairs of eyelets. Welt detail around upper. Rounded shape. Chunky lug soles.',
       'Sneakers. Made of leather with a suede finish. Laces with five pairs of eyelets. Chunky soles.',
       'Ankle boots. Made of leather with a suede finish. Faux shearling interior and side detail. Rounded shape. Welt around upper. Back pull tab. Chunky lug soles.',
       'Sneakers. Upper in a combination of pieces and textures. Shoelaces with six pairs of eyelets at different heights. Chunky irregular design soles. Retro-inspired design.',
       'Sandals. Made of leather with a suede finish. Two wide straps at instep with buckles. Insole with anatomical shaped footbed. Welt around upper. Chunky lug soles.',
       'High shaft boots. Lacing with eight pairs of eyelets. Back pull tab for ease. Rounded shape. Chunky lug soles.',
       'Loafers. Made of leather with a suede finish. Ornamental saddle detail at instep. Rounded shape. Contrasting colored sole.',
       'Sneakers. Monochromatic. Upper in a combination of pieces. Closure with three adhesive straps. Slightly chunky sole.',
       'Running shoes. Upper in a combination of pieces and finishes. Lacing with six pairs of eyelets. Chunky soles with irregular design. Lug soles. Trek style.',
       'High top sneakers. Lacing with nine pairs of eyelets. Contrasting foxing around the upper. Chunky rubberized soles.',
       'Sneakers. Made of leather. Upper in a combination of pieces and finishes. Lacing with six pairs of eyelets. Rounded shape. Chunky sole.',
       'Running shoes. Made of suede leather. Upper in a combination of materials and colors. Lacing with six pairs of eyelets. Chunky soles with irregular design.',
       'Sandals. Made of leather. Three woven wide straps at instep. Chunky sole.',
       'Sneakers. Made of leather with a suede finish. Contrast lacing with seven pairs of eyelets. Welt around upper. Chunky sole.',
       'Woven V-neckline long sleeve sweater. Asymmetric hem.',
       'Sweater made with 22% wool and 10% alpaca. Round neck and long sleeves. Faux pearl appliqué.',
       'Sweater with high collar and long sleeves. Front pocket. Side vents at hem. Rib trim.',
       'Sweater with high collar and long sleeves. Front zip closure.',
       'Round neck long sleeve sweater. Metallic fabric detail and frayed trim.',
       'Wool and silk blend sweater. Asymmetric neckline and long sleeves.',
       'Sweater made with 80% wool and 20% cashmere. Round neck and long sleeves.',
       'Sweater made with 31% wool and 28% alpaca. Round neck and long sleeves.',
       'Wool and silk blend top. High collar and long sleeves.',
       'Sweater made with 95% cashmere. V-neck and long sleeves. Rib trim.',
       'Sweater made with 63% alpaca. Round neck and long sleeves.',
       'Sweater made with 20% wool and 17% alpaca. Crew neck and long sleeves. Tonal rib trim.',
       'Sweater made with 31% wool. Round neck and long sleeves. Rib trim.',
       'Sweater made of soft touch fabric. Round neckline with jewel appliqués and long sleeves.',
       'Round neck short sleeve sweater. Soft feel faux fur fabric. Jewel appliqués.',
       'Round neck long sleeve sweater. Side slit at hem with metal bead appliqués.',
       'Basic sweater with round neck and long sleeves. Side button details at shoulders.',
       'Round neck sweater with jewel appliqués and long sleeves. Back opening with button closure.',
       'Round neck long sleeve sweater. Contrasting piping detail. Rib trim.',
       'Cropped fine knit sweater with round neck and long sleeves.',
       'Round neck long sleeve sweater. Openwork detail with rips.',
       'Round neck long sleeve sweater. Fitted waist with side ruching.',
       'V-neck sweater with long sleeves. Rib trim.',
       'Round neck long sleeve sweater. Rib trim.',
       'V-neck cropped sweater with long sleeves. Front patch pockets. Contrast topstitching.',
       'Long sleeve high collar cropped sweater. Frayed hem.',
       'Long sleeve round neck sweater. Side vents at hem. Rib trim.',
       'V-neck sweater with long sleeves. Side vents at hem.',
       'Ribbed sweater with round neck and long sleeves. Ripped hem.',
       'Sweater made of 100% wool. Round neck and long sleeves. Ribbed trim.',
       'Short sweater with round neck and long sleeves.',
       'V-neck sweater with long sleeves.',
       'High collar sweater with long sleeves. Open back detail and pearl appliqués. Back button closure.',
       'Round neck long sleeve sweater. Tonal pearl appliqués and open back with tie.',
       'Relaxed fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Patch pockets at hip. Front button closure.',
       'Regular fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Chest patch pockets. Front button closure.',
       'Relaxed fit overshirt. Lapel collar and long sleeves with buttoned cuffs. Chest patch pockets. Front button closure.',
       'Baggy jeans. Five pockets. Washed effect. Front zip and button closure.',
       'Baggy jeans. Self belt at waist. Front pockets and back patch pockets. Washed effect. Front button closure.',
       'Baggy fit jeans. Five pockets. Washed effect. Front zip and button closure.',
       'Flared jeans. Patch pockets with flaps at hip. Patch pocket appliqués at legs. Washed effect. Adjustable hem with zippers. Front zipper and crossover button closure.',
       'Wide fit jeans. Adjustable interior elastic waistband with front pleats. Front pockets and back patch pockets. Washed effect. Front zip and button closure.',
       'Relaxed fit shirt made of denim fabric. Lapel collar and short sleeves. Chest patch pocket. Washed effect. Front button closure.',
       'Straight fit jeans. Five pockets. Washed effect with rips at legs. Front button closure.',
       'Sweater made of 30% wool thread. Round neck and long sleeves. Rib trim.',
       'High collar sweater with front zipper. Long sleeves. Rib trim.',
       'Round neck long sleeve full cut sweater. Rib trim.',
       'Cotton blend sweater. Round neck and long sleeves. Contrast interior. Rib trim.',
       'Full cut cotton knit sweater. Round neck and long sleeves. Rib trim.',
       'Slim fit shirt. Round neck and short sleeves.',
       'Cropped fit T-shirt with round neck and short sleeves. Contrasting front and back prints. Washed effect.',
       'Roomy T-shirt made of dense cotton. Round neck and short sleeves.',
       'Boxy fit T-shirt with round neck and short sleeves. Contrasting prints at shoulder and back.',
       'Boxy fit T-shirt. Round neck and short sleeves. Velvet effect print with contrast text.',
       'Cropped shirt. Round neckline. Contrasting front print. Washed effect. Irregular trim.',
       'Cotton knit tank top. Round neck with front button closure. Rib trim.',
       'Oversized T-shirt. Round neck and short sleeves.',
       'Regular fit T-shirt. Round neck and short sleeves.',
       'Full cut T-shirt made of mesh textured fabric. Contrast rib V-neckline and short sleeves. Front contrast printed text.',
       'Full cut T-shirt with crew neck and short sleeves. Contrasting front and back prints. Washed effect.',
       'Full cut T-shirt with round neck and short sleeves. Front tonal raised text. Washed effect.',
       'Cropped fit knit shirt. Round neck and long sleeves. Washed effect.',
       'Slim fit shirt made of wrinkle effect fabric. Round neck and long sleeves.',
       'Knit shirt in viscose blend fabric. Mock neck and short sleeves. Rib trim.',
       'Relaxed fit T-shirt with round neck and short sleeves.',
       'Cotton knit T-shirt. Round neck and short sleeves.',
       'RETRO SNEAKERS'], dtype=object)
In [37]:
data["description"].value_counts()
Out[37]:
description
Varsity jacket with elastic collar and long sleeves. Welt pockets at hip and interior pocket. Embroidered appliqué and contrast front and back patches. Rib trim. Front snap button closure.    333
Overshirt made of stretchy fabric. Lapel collar and long sleeves with snap buttoned cuffs. Chest patch pockets. Front snap button closure.                                                      197
Slightly cropped denim jacket. Lapel collar and long sleeves with buttoned cuffs. Flap patch pocket at chest and side hip. Washed effect. Front button closure.                                 179
Jacket made of technical fabric with padded interior. Tonal elastic rib high collar. Long sleeves. Welt pockets at hip and interior pocket. Interior elastic finish. Front zip closure.         178
Jacket with lightly padded interior. Corduroy lapel collar. Long sleeves. Patch pockets at hip. Front button closure.                                                                           177
                                                                                                                                                                                               ... 
Relaxed fit reversible overshirt. Italian collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.                                                                 65
Relaxed fit overshirt made of viscose blend fabric. Lapel collar and long sleeves with buttoned cuffs. Chest patch pocket. Front button closure.                                                 64
Cropped fit knit shirt. Round neck and long sleeves. Washed effect.                                                                                                                              59
High-top sneakers. Upper in a combination of pieces. Laces with ten pairs of eyelets. Chunky sole.                                                                                               59
Sweater with high collar and long sleeves. Front zip closure.                                                                                                                                    58
Name: count, Length: 221, dtype: int64
In [38]:
data["description"]
Out[38]:
0        Puffer jacket made of tear-resistant ripstop f...
1        Straight fit blazer. Pointed lapel collar and ...
2        Slim fit jacket. Notched lapel collar. Long sl...
3        Slim fit jacket made of viscose blend fabric. ...
4        Jacket made of faux leather faux shearling wit...
                               ...                        
20247    Running shoes. Upper in a combination of piece...
20248        Slim fit shirt. Round neck and short sleeves.
20249    Ankle boots. Made of leather with a suede fini...
20250                                       RETRO SNEAKERS
20251    Relaxed fit overshirt made of linen fabric. La...
Name: description, Length: 20252, dtype: object
In [39]:
data["currency"].unique()
Out[39]:
array(['USD'], dtype=object)
In [40]:
data["currency"].value_counts()
Out[40]:
currency
USD    20252
Name: count, dtype: int64
In [41]:
data["terms"]
Out[41]:
0        jackets
1        jackets
2        jackets
3        jackets
4        jackets
          ...   
20247      jeans
20248    jackets
20249      shoes
20250    jackets
20251      shoes
Name: terms, Length: 20252, dtype: object
In [42]:
data["terms"].unique()
Out[42]:
array(['jackets', 'shoes', 'sweaters', 'jeans', 't-shirts'], dtype=object)
In [43]:
data["terms"].value_counts()
Out[43]:
terms
jackets     11232
sweaters     3257
t-shirts     2646
shoes        2458
jeans         659
Name: count, dtype: int64
In [44]:
data["section"].unique()
Out[44]:
array(['MAN', 'WOMAN'], dtype=object)
In [45]:
data["section"].value_counts()
Out[45]:
section
WOMAN    13254
MAN       6998
Name: count, dtype: int64
In [46]:
import matplotlib.pyplot as plt
import seaborn as sns
data["section"].value_counts().plot(kind = "bar")
plt.title("Section count")
plt.show()
In [47]:
sns.histplot(data = data,x = "section")
D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

Out[47]:
<Axes: xlabel='section', ylabel='Count'>
In [48]:
count = data["section"].value_counts()
colors = ["skyblue","yellow"] * (len(count)// 2+1)
count.plot(kind = "bar",color = colors[:len(count)])
plt.title("section count plot")
plt.show()
In [49]:
data["terms"].value_counts().plot(kind = "bar")
plt.title("Terms counts")
plt.show()
In [50]:
data["season"].unique()
Out[50]:
array(['Winter', 'Autumn', 'Spring', 'Summer'], dtype=object)
In [51]:
import matplotlib.pyplot as plt
import seaborn as sns

# Get value counts
counts = data["season"].value_counts()

# Choose a color palette with enough distinct colors
colors = sns.color_palette("Set2", len(counts))  # You can also try "pastel", "tab10", etc.

# Plot with custom colors
counts.plot(kind="bar", color=colors)

plt.title("Season Sales Count")
plt.xlabel("Season")
plt.ylabel("Count")
plt.xticks(rotation=90)
plt.tight_layout()
plt.show()
In [52]:
import seaborn as sns
import matplotlib.pyplot as plt

for col in cat_cols:
    plt.figure(figsize=(6,3))
    sns.countplot(data= data, x=col)
    plt.title(f"Distribution of {col}")
    plt.xticks(rotation=45)
    plt.show()
In [53]:
for col in num_cols:
    plt.figure(figsize=(6,3))
    sns.histplot(data[col], kde=True, bins=20)
    plt.title(f"Distribution of {col}")
    plt.show()

    sns.boxplot(x=data[col])
    plt.title(f"Boxplot of {col}")
    plt.show()
D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

In [54]:
sns.boxplot(data = data,x = "price")
plt.title("Box plot of price")
plt.show()
In [55]:
data["price"].unique()
Out[55]:
array([ 78.99,  14.99,  71.95,  30.99,  22.99,  25.95,  87.99,  24.  ,
        32.95,  39.95,  15.95,  49.99,  69.99,  28.99,  29.99,  25.99,
        77.99,  79.99,  39.99,  19.95,  21.99,  24.95,  32.99,  31.99,
        16.99,  45.99,  99.99,  19.99,  43.95,  74.99,  59.99,  86.99,
        22.95,  17.95,  29.  ,  29.95,  22.  ,  35.95,  92.99,  49.95,
        41.95,  53.  ,  15.  ,  89.95,  35.99,  37.99,  38.99,  33.99,
        64.99,  16.95,  69.95,  65.95,  15.99,  79.95,  12.95,  34.99,
        80.95,  76.  ,  18.99,  17.99,  34.  ,  33.95,  17.  ,  23.95,
        43.99,  55.95,  61.99,  20.99,  98.95,  19.  ,  32.  ,  54.99,
        56.95,  45.95,  55.99,  31.95,  47.99,  26.99, 129.99,  21.95,
        74.95,  51.99, 103.99,  41.  ,  53.99,  66.95,  50.99, 130.99,
        20.95,  77.95,  25.  ,  33.  ,  82.95,  18.95,  23.99,  52.99,
        48.  ,  73.95,  64.  ,  62.99,  63.99,  67.99,  65.99,  12.99,
        40.99,  41.99,  83.95,  84.99,  28.95,  59.  ,  95.  ,  24.99,
        71.  ,  79.  ,  53.95,  69.  ,  23.  ,  42.  ,  42.99,  37.95,
        68.99, 119.99,  52.95,  66.  ,  63.  ,  30.95,  54.95,  60.99,
        36.99,  26.  , 127.99, 107.  ,  39.  ,  14.  ,  36.95, 119.95,
        57.95,  13.99,  57.99,  59.95,  47.95,  73.99,  48.95,  27.95,
        65.  ,  88.95,  48.99, 108.95,  30.  , 128.99, 106.99,  27.  ,
        13.  ,  42.95,  75.99,  64.95,  38.95,  38.  ,  14.95,  61.95,
        83.  ,  66.99,  89.99,  58.99,  45.  ,  44.99, 128.  ,  27.99,
       126.99, 109.95,  51.95,  75.  ,  34.95,  49.  ,  76.95,  44.95,
        86.95,  67.  ,  31.  ,  82.99,  13.95,  90.99,  75.95,  71.99,
        21.  ,  68.  , 119.  ,  46.  ,  70.95,  63.95,  81.99, 108.  ,
        18.  ,  47.  ,  35.  ,  40.95, 107.99,  62.95,  20.  ,  60.95,
        88.99,  85.99,  93.95,  84.  ,  43.  ,  26.95,  50.  ,  50.95,
        28.  ,  82.  ,  46.95,  95.99, 104.95, 103.95, 100.  ,  72.95,
        89.  , 132.99,  87.95,  16.  , 105.99,  72.99,  99.95,  78.95,
        46.99, 102.  ,  96.99,  54.  , 132.95,  72.  ,  97.99, 110.95,
        51.  ,  44.  , 110.99, 109.99,  83.99,  92.  ,  87.  ,  76.99,
        68.95, 107.95,  36.  ,  61.  ,  40.  , 108.99,  67.95,  85.95,
        70.99,  86.  ,  56.  , 100.99,  56.99,  96.95, 105.  ,  85.  ,
       102.99,  73.  , 127.95, 130.95,  84.95,  55.  ,  80.99,  62.  ,
       113.99,  81.95, 133.99,  52.  ,  60.  ,  98.99,  74.  , 134.95,
        88.  , 126.95,  94.95,  80.  ,  95.95,  58.95, 104.99, 105.95,
       129.95, 113.95,  78.  ,  77.  ,  94.99,  97.95,  99.  , 101.99,
        91.99, 128.95,  58.  , 102.95, 117.99, 111.99,  70.  , 126.  ,
        57.  , 131.99,  93.99, 106.95,  37.  , 100.95,  91.  , 112.99,
        12.  ,  94.  , 111.  , 131.95, 131.  , 129.  ,  91.95, 111.95,
       133.95, 114.99, 106.  ,  81.  , 115.95, 134.99,  90.95, 115.99,
        96.  , 112.95, 130.  , 133.  , 109.  ,  97.  ,  90.  , 132.  ,
       103.  , 101.95])
In [56]:
data["price"].value_counts()
Out[56]:
price
19.99     662
29.99     621
25.99     599
39.99     530
22.99     518
         ... 
102.00      1
92.00       1
91.00       1
112.99      1
101.95      1
Name: count, Length: 330, dtype: int64
In [57]:
data["price"].max()
Out[57]:
134.99
In [58]:
data.agg({"price": ["max", "min","sum","mean"]})
Out[58]:
price
max 134.990000
min 12.000000
sum 849552.380000
mean 41.949061
In [59]:
data.agg({"price" : ["sum","mean","max","min"]})
Out[59]:
price
sum 849552.380000
mean 41.949061
max 134.990000
min 12.000000
In [60]:
data.agg({"Sales Volume" : ["sum","mean","max","min"]})
Out[60]:
Sales Volume
sum 2.222455e+07
mean 1.097400e+03
max 1.940000e+03
min 5.180000e+02
In [61]:
data["Sales Volume"] = pd.to_numeric(data["Sales Volume"], errors="coerce")
In [62]:
data["Sales Volume"]
Out[62]:
0        1243
1        1429
2        1168
3        1348
4        1602
         ... 
20247    1754
20248     872
20249    1360
20250     892
20251     859
Name: Sales Volume, Length: 20252, dtype: int64
In [63]:
data.agg({"Sales Volume" : ["sum","mean","max","min"]})
Out[63]:
Sales Volume
sum 2.222455e+07
mean 1.097400e+03
max 1.940000e+03
min 5.180000e+02
In [64]:
data["Sales Volume"].describe()
Out[64]:
count    20252.000000
mean      1097.400454
std        298.234609
min        518.000000
25%        849.000000
50%        990.000000
75%       1364.250000
max       1940.000000
Name: Sales Volume, dtype: float64
In [65]:
data["Sales Volume"].sum()
Out[65]:
22224554
In [66]:
data["Sales Volume"].unique()
Out[66]:
array([1243, 1429, 1168, ..., 1756, 1845,  599], dtype=int64)
In [67]:
data["Sales Volume"].value_counts()
Out[67]:
Sales Volume
848     60
829     59
864     54
867     54
838     54
        ..
1879     1
1740     1
1912     1
1782     1
599      1
Name: count, Length: 1284, dtype: int64
In [68]:
data[data["Sales Volume"].isin(data["Sales Volume"].value_counts().sort_values(ascending=True).index)]
Out[68]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
20247 219627 Front of Store Yes clothing No 1754 Zara https://www.zara.com/us/en/suit-jacket-in-100-... CROPPED WASHED T-SHIRT CHARCOAL Running shoes. Upper in a combination of piece... 31.95 USD jeans WOMAN Summer Linen Blend India
20248 219628 Aisle No clothing No 872 Zara https://www.zara.com/us/en/fleece-overshirt-p0... SATIN WOVEN LEATHER SLIDES STONE Slim fit shirt. Round neck and short sleeves. 49.99 USD jackets WOMAN Spring Linen China
20249 219629 Aisle Yes clothing No 1360 Zara https://www.zara.com/us/en/faux-suede-patch-ja... RELAXED CROPPED LEATHER JACKET CHARCOAL Ankle boots. Made of leather with a suede fini... 20.99 USD shoes WOMAN Spring Polyester China
20250 219630 Aisle No clothing No 892 Zara https://www.zara.com/us/en/fine-knit-crop-swea... SLIM BASIC 100% WOOL SWEATER BURGUNDY RETRO SNEAKERS 64.95 USD jackets WOMAN Winter Polyester Spain
20251 219631 Aisle No clothing No 859 Zara https://www.zara.com/us/en/contrasting-patches... KNIT TUXEDO JACKET BURGUNDY Relaxed fit overshirt made of linen fabric. La... 64.99 USD shoes MAN Summer Linen Turkey

20252 rows × 17 columns

In [69]:
data["material"].unique()
Out[69]:
array(['Polyester', 'Cotton', 'Wool Blend', 'Acrylic', 'Wool', 'Viscose',
       'Linen', 'Denim', 'Linen Blend', 'Satin', 'Silk'], dtype=object)
In [70]:
data["material"].value_counts()
Out[70]:
material
Cotton         3851
Wool           3805
Wool Blend     3373
Polyester      2775
Linen          2573
Denim          1027
Viscose         990
Acrylic         881
Linen Blend     807
Satin           132
Silk             38
Name: count, dtype: int64
In [71]:
data["material"].value_counts().plot(kind = "bar")
plt.title("material counts")
plt.show()
In [72]:
data["origin"].unique()
Out[72]:
array(['Brazil', 'Turkey', 'Morocco', 'China', 'Portugal', 'India',
       'Bangladesh', 'Vietnam', 'Spain', 'Cambodia', 'Argentina',
       'Pakistan'], dtype=object)
In [73]:
data["origin"].value_counts().plot(kind = "bar")
Out[73]:
<Axes: xlabel='origin'>
In [74]:
import seaborn as sns
import matplotlib.pyplot as plt

# Get counts
count = data["origin"].value_counts().reset_index()
count.columns = ["origin", "count"]

# Plot
sns.barplot(data=count, x="origin", y="count")
plt.title("Origin Sales Count")
plt.xlabel("Origin")
plt.ylabel("Sales Count")
plt.xticks(rotation = 45)  # Optional: rotate labels if needed
plt.tight_layout()
plt.show()
In [75]:
count = data["terms"].value_counts().reset_index()
count.columns = ["terms","count"]
sns.barplot(data = count,x = "terms",y = "count")
plt.title("terms sales distibution")
plt.xticks(rotation = 45)
plt.show()
In [76]:
grouped = data.groupby("section")["price"].agg(["sum","mean","max","min"])
grouped
Out[76]:
sum mean max min
section
MAN 294796.18 42.125776 134.95 12.0
WOMAN 554756.20 41.855757 134.99 12.0
In [77]:
grouped = data.groupby("section")["price"].size().reset_index(name = "count")
grouped
Out[77]:
section count
0 MAN 6998
1 WOMAN 13254
In [78]:
grouped_sales = data.groupby("section")["Sales Volume"].size().reset_index(name = "count")
grouped_sales
Out[78]:
section count
0 MAN 6998
1 WOMAN 13254
In [79]:
grouped_sales = data.groupby("section")["Sales Volume"].agg(["sum","mean","max","min"])
grouped_sales
Out[79]:
sum mean max min
section
MAN 7163407 1023.636325 1798 518
WOMAN 15061147 1136.347291 1940 582
In [80]:
data["Sales Volume"].sum()
Out[80]:
22224554
In [81]:
data["Sales Volume"].count()
Out[81]:
20252
In [82]:
data["Sales Volume"].mean()
Out[82]:
1097.4004542761209
In [83]:
data.head()
Out[83]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
In [84]:
grouped_season = data.groupby("season")["Sales Volume"].size().reset_index(name = "count")
grouped_season
Out[84]:
season count
0 Autumn 7665
1 Spring 4537
2 Summer 2906
3 Winter 5144
In [85]:
grouped_season = data.groupby("season")["Sales Volume"].agg(["sum","mean","max","min","count"])
grouped_season
Out[85]:
sum mean max min count
season
Autumn 7993214 1042.819830 1737 518 7665
Spring 4746716 1046.223496 1719 543 4537
Summer 3442417 1184.589470 1940 575 2906
Winter 6042207 1174.612558 1940 591 5144
In [86]:
filtered_data = data[(data["Sales Volume"] >= 1000) & (data["Promotion"] == "No")].shape[0]
filtered_data
Out[86]:
1507
In [87]:
data[(data["Sales Volume"] >= 500) & (data["Promotion"] == "No")].shape[0]
Out[87]:
11812
In [88]:
data[data["Sales Volume"] >= 500]
Out[88]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
20247 219627 Front of Store Yes clothing No 1754 Zara https://www.zara.com/us/en/suit-jacket-in-100-... CROPPED WASHED T-SHIRT CHARCOAL Running shoes. Upper in a combination of piece... 31.95 USD jeans WOMAN Summer Linen Blend India
20248 219628 Aisle No clothing No 872 Zara https://www.zara.com/us/en/fleece-overshirt-p0... SATIN WOVEN LEATHER SLIDES STONE Slim fit shirt. Round neck and short sleeves. 49.99 USD jackets WOMAN Spring Linen China
20249 219629 Aisle Yes clothing No 1360 Zara https://www.zara.com/us/en/faux-suede-patch-ja... RELAXED CROPPED LEATHER JACKET CHARCOAL Ankle boots. Made of leather with a suede fini... 20.99 USD shoes WOMAN Spring Polyester China
20250 219630 Aisle No clothing No 892 Zara https://www.zara.com/us/en/fine-knit-crop-swea... SLIM BASIC 100% WOOL SWEATER BURGUNDY RETRO SNEAKERS 64.95 USD jackets WOMAN Winter Polyester Spain
20251 219631 Aisle No clothing No 859 Zara https://www.zara.com/us/en/contrasting-patches... KNIT TUXEDO JACKET BURGUNDY Relaxed fit overshirt made of linen fabric. La... 64.99 USD shoes MAN Summer Linen Turkey

20252 rows × 17 columns

In [89]:
num_cols = ["price","Sales Volume"]
sns.pairplot(data[num_cols])
plt.show()

sns.heatmap(data[num_cols].corr(), annot=True, cmap='coolwarm')
plt.title("Correlation Heatmap")
plt.show()
D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

In [90]:
sns.barplot(data = data,x = "section",y = "price")
Out[90]:
<Axes: xlabel='section', ylabel='price'>
In [91]:
sns.barplot(data = data,x = "terms",y = "price",hue = "section")
Out[91]:
<Axes: xlabel='terms', ylabel='price'>
In [92]:
import plotly.express as px
from plotly.offline import iplot
fig = px.box(x = data["Sales Volume"],
labels={"x":"Age"},
 title="5-Number-Summary(Box Plot) of Sales Volume")
iplot(fig)
In [93]:
import plotly.express as px
from plotly.offline import iplot
fig = px.box(data_frame=data,x = "price",labels = {"price" : "Price"},title = "Summary of price box plot")
iplot(fig)
In [94]:
import plotly.express as px
from plotly.offline import iplot, init_notebook_mode

init_notebook_mode(connected=True)  # Enables offline mode in Jupyter

# Create box plot
fig = px.box(data_frame=data, x="price", labels={"price": "Price"}, title="Summary of Price")

iplot(fig)
In [95]:
# Remove outliers using IQR method
Q1 = data["price"].quantile(0.25)
Q3 = data["price"].quantile(0.75)
IQR = Q3 - Q1
print(IQR)
filtered_data = data[(data["price"] >= Q1 - 1.5 * IQR) & (data["price"] <= Q3 + 1.5 * IQR)]
filtered_data
30.000000000000004
Out[95]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
20247 219627 Front of Store Yes clothing No 1754 Zara https://www.zara.com/us/en/suit-jacket-in-100-... CROPPED WASHED T-SHIRT CHARCOAL Running shoes. Upper in a combination of piece... 31.95 USD jeans WOMAN Summer Linen Blend India
20248 219628 Aisle No clothing No 872 Zara https://www.zara.com/us/en/fleece-overshirt-p0... SATIN WOVEN LEATHER SLIDES STONE Slim fit shirt. Round neck and short sleeves. 49.99 USD jackets WOMAN Spring Linen China
20249 219629 Aisle Yes clothing No 1360 Zara https://www.zara.com/us/en/faux-suede-patch-ja... RELAXED CROPPED LEATHER JACKET CHARCOAL Ankle boots. Made of leather with a suede fini... 20.99 USD shoes WOMAN Spring Polyester China
20250 219630 Aisle No clothing No 892 Zara https://www.zara.com/us/en/fine-knit-crop-swea... SLIM BASIC 100% WOOL SWEATER BURGUNDY RETRO SNEAKERS 64.95 USD jackets WOMAN Winter Polyester Spain
20251 219631 Aisle No clothing No 859 Zara https://www.zara.com/us/en/contrasting-patches... KNIT TUXEDO JACKET BURGUNDY Relaxed fit overshirt made of linen fabric. La... 64.99 USD shoes MAN Summer Linen Turkey

19611 rows × 17 columns

In [96]:
data.shape
Out[96]:
(20252, 17)
In [97]:
data["name"]
Out[97]:
0                            BASIC PUFFER JACKET
1                                  TUXEDO JACKET
2                           SLIM FIT SUIT JACKET
3                            STRETCH SUIT JACKET
4                            DOUBLE FACED JACKET
                          ...                   
20247            CROPPED WASHED T-SHIRT CHARCOAL
20248           SATIN WOVEN LEATHER SLIDES STONE
20249    RELAXED CROPPED LEATHER JACKET CHARCOAL
20250      SLIM BASIC 100% WOOL SWEATER BURGUNDY
20251                KNIT TUXEDO JACKET BURGUNDY
Name: name, Length: 20252, dtype: object
In [98]:
import seaborn as sns
import matplotlib.pyplot as plt

sns.displot(data["price"], kde=True)
plt.title("Distribution of Price")
plt.xlabel("Price")
plt.ylabel("Frequency")
plt.show()
D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

In [99]:
import matplotlib.pyplot as plt

plt.plot(data["Sales Volume"])
plt.title("Line Plot of Sales Volume")
plt.xlabel("Index")
plt.ylabel("Sales Volume")
plt.grid(True)
plt.show()
In [100]:
import matplotlib.pyplot as plt

plt.figure(figsize=(10, 6))

plt.plot(data.index, data["price"], label="Price", color="blue")
plt.plot(data.index, data["Sales Volume"], label="Sales Volume", color="green")

plt.title("Price vs Sales Volume Over Index")
plt.xlabel("Index")
plt.ylabel("Value")
plt.legend()
plt.grid(True)
plt.tight_layout()
plt.show()
In [101]:
grouped_Product_Position = data.groupby("Product Position")["Sales Volume"].size().reset_index(name = "count")
grouped_Product_Position
Out[101]:
Product Position count
0 Aisle 7810
1 End-cap 6791
2 Front of Store 5651
In [102]:
grouped_Product_Position = data.groupby(["Product Position","season"])["Sales Volume"].agg(["max","min","mean","median"])
grouped_Product_Position
Out[102]:
max min mean median
Product Position season
Aisle Autumn 1702 518 1036.942261 921.0
Spring 1719 543 1037.852730 920.0
Summer 1908 657 1173.484417 1047.0
Winter 1929 616 1168.373687 1038.0
End-cap Autumn 1662 534 1041.697674 927.0
Spring 1717 559 1055.492803 936.0
Summer 1886 621 1188.139202 1061.0
Winter 1940 591 1181.338070 1053.0
Front of Store Autumn 1737 533 1052.184087 931.0
Spring 1679 580 1047.529644 932.0
Summer 1940 575 1195.759305 1069.0
Winter 1917 614 1175.376374 1050.5
In [103]:
import matplotlib.pyplot as plt
import seaborn as sns
grouped = data.groupby(["Product Position","season"])["Sales Volume"].size().reset_index(name = "count")
plt.figure(figsize = (15,8))
sns.barplot(x = "season",y = "Sales Volume",hue = "Product Position",data = data)
plt.title("season wise product postion sales distibution")
plt.xlabel("Season")
plt.ylabel("Sales volume")
plt.tight_layout()
plt.show()
In [104]:
import matplotlib.pyplot as plt
import seaborn as sns
grouped = data.groupby(["Product Position","season"])["Sales Volume"].size().reset_index(name = "count")
plt.figure(figsize = (15,6))
sns.barplot(x = "Product Position",y = "count",hue = "season",data = grouped)
plt.title("season wise product postion sales distibution")
plt.xlabel("Season")
plt.ylabel("Sales volume")
plt.tight_layout()
plt.show()
In [105]:
data.head()
Out[105]:
Product ID Product Position Promotion Product Category Seasonal Sales Volume brand url name description price currency terms section season material origin
0 185102 Aisle Yes clothing Yes 1243 Zara https://www.zara.com/us/en/basic-puffer-jacket... BASIC PUFFER JACKET Puffer jacket made of tear-resistant ripstop f... 78.99 USD jackets MAN Winter Polyester Brazil
1 188771 Aisle Yes clothing No 1429 Zara https://www.zara.com/us/en/tuxedo-jacket-p0889... TUXEDO JACKET Straight fit blazer. Pointed lapel collar and ... 14.99 USD jackets MAN Autumn Cotton Turkey
2 180176 End-cap Yes clothing Yes 1168 Zara https://www.zara.com/us/en/slim-fit-suit-jacke... SLIM FIT SUIT JACKET Slim fit jacket. Notched lapel collar. Long sl... 71.95 USD jackets WOMAN Autumn Polyester Morocco
3 112917 Aisle Yes clothing No 1348 Zara https://www.zara.com/us/en/stretch-suit-jacket... STRETCH SUIT JACKET Slim fit jacket made of viscose blend fabric. ... 30.99 USD jackets MAN Spring Polyester China
4 192936 End-cap Yes clothing Yes 1602 Zara https://www.zara.com/us/en/double-faced-jacket... DOUBLE FACED JACKET Jacket made of faux leather faux shearling wit... 22.99 USD jackets WOMAN Winter Wool Blend China
In [106]:
filterd = data[data["price"] >= 50]
result = (filterd.groupby("terms")["price"]
          .size()
          .reset_index(name = "count")
          .sort_values(by = "count",ascending = False)
         )
print(result)
      terms  count
0   jackets   3002
3  sweaters    888
4  t-shirts    776
2     shoes    699
1     jeans    201
In [107]:
filtered = data[data["price"] >= 50]
result = (
    filtered.groupby("terms")["price"]
    .mean()
    .sort_values(ascending=False)
)
print(result)
terms
t-shirts    74.076959
jackets     73.703371
shoes       73.447597
sweaters    73.042309
jeans       72.165721
Name: price, dtype: float64
In [108]:
filterd = data[data["Sales Volume"] >= 1000]
result = (filterd.groupby("Promotion")["Sales Volume"]
         .mean()
         .sort_values(ascending = False)
         )
print(result)
Promotion
Yes    1413.406176
No     1057.587259
Name: Sales Volume, dtype: float64
In [109]:
filterd = data[data["Sales Volume"] >= 1000]
result = (filterd.groupby("Promotion")["Sales Volume"]
         .size()
         .reset_index(name = "count")
         .sort_values(by = "count",ascending = False)
         )
print(result)
  Promotion  count
1       Yes   8420
0        No   1507
In [110]:
sns.histplot(data["price"],kde = True)
D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

Out[110]:
<Axes: xlabel='price', ylabel='Count'>
In [111]:
x = data["season"]
y = data["Sales Volume"] 
import matplotlib.pyplot as plt
import seaborn as sns
plt.scatter(x,y,color = "green",linestyle = "--",marker = "s")
plt.title("season based sales volume")
plt.show()
In [112]:
import matplotlib.pyplot as plt
import seaborn as sns

x = data["Sales Volume"]
y = data["price"]

# Use seaborn's scatterplot correctly
sns.scatterplot(x=x, y=y, color="green", marker="s")

plt.title("Product Category by price")
plt.xlabel("Product Category")
plt.ylabel("price")
plt.grid(True)
plt.show()
In [113]:
sns.histplot(data["Sales Volume"],kde = True)
D:\Users\tamilarasi\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning:

use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.

Out[113]:
<Axes: xlabel='Sales Volume', ylabel='Count'>
In [ ]:
 
In [ ]:
 
In [ ]:
 
In [ ]:
 
In [ ]: